Actuators,
Год журнала:
2024,
Номер
13(10), С. 413 - 413
Опубликована: Окт. 13, 2024
In
fields
such
as
manufacturing
and
aerospace,
remaining
useful
life
(RUL)
prediction
estimates
the
failure
time
of
high-value
assets
like
industrial
equipment
aircraft
engines
by
analyzing
series
data
collected
from
various
sensors,
enabling
more
effective
predictive
maintenance.
However,
significant
temporal
diversity
operational
complexity
during
operation
make
it
difficult
for
traditional
single-scale,
single-dimensional
feature
extraction
methods
to
effectively
capture
complex
dependencies
multi-dimensional
interactions.
To
address
this
issue,
we
propose
a
Dual-Path
Interaction
Network,
integrating
Multiscale
Temporal-Feature
Convolution
Fusion
Module
(MTF-CFM)
Dynamic
Weight
Adaptation
(DWAM).
This
approach
adaptively
extracts
information
across
different
scales,
interaction
information.
Using
Commercial
Modular
Aero-Propulsion
System
Simulation
(C-MAPSS)
dataset
comprehensive
performance
evaluation,
our
method
achieved
RMSE
values
0.0969,
0.1316,
0.086,
0.1148;
MAPE
9.72%,
14.51%,
8.04%,
11.27%;
Score
results
59.93,
209.39,
67.56,
215.35
four
categories.
Furthermore,
MTF-CFM
module
demonstrated
an
average
improvement
7.12%,
10.62%,
7.21%
in
RMSE,
MAPE,
multiple
baseline
models.
These
validate
effectiveness
potential
proposed
model
improving
accuracy
robustness
RUL
prediction.
Structural Health Monitoring,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 13, 2025
Characterizing
equipment
performance
degradation
and
predicting
remaining
useful
life
(RUL)
are
critical
aspects
of
predictive
maintenance
in
mechanical
systems.
The
foundation
effective
RUL
prediction
lies
constructing
health
indicator
(HI)
based
on
condition
monitoring
signals
that
accurately
reflect
status.
In
addition,
the
individual
variability
uncertainty
process
often
make
it
challenging
for
a
single
path
to
represent
entire
fully.
To
address
these
issues,
this
article
introduces
novel
framework
characterization
prediction.
Initially,
we
constructed
HI
using
Wasserstein
distance
Cumulative
sum
(CUMSUM)
control
chart.
This
approach
not
only
captures
changes
signal
probability
distribution
during
but
also
exhibits
strong
monotonicity,
trendability,
robustness.
Next,
propose
dynamic
first
time
(FPT)
identification
method
Chebyshev’s
inequality,
which
effectively
mitigates
influence
outliers
minor
fluctuations.
Additionally,
develop
matching
multipath
adaptive
drift
linear
multifractional
Lévy
stable
motion
(DPM-MPALMLSM)
model
MPALMLSM
incorporates
multiple
paths
capture
non-Gaussian
characteristics,
long-range
dependence
features,
multifractal
properties
process,
with
coefficients
dynamically
updated
as
data
evolves.
method,
grounded
evaluation,
facilitates
efficient
switching
between
paths,
enhancing
accuracy.
effectiveness
precision
proposed
demonstrated
full-life
testing
from
heavy
truck
transmissions,
XJTU-SY
IMS
benchmark
bearing
datasets.
